Consistency of noise covariance estimation in joint input–output closed-loop subspace identification with application in LQG benchmarking

Abstract The LQG trade-off curve has been used as a benchmark for control loop performance assessment. The subspace approach to estimating the LQG benchmark has been proposed in the literature which requires certain intermediate matrices in subspace identification as well as the covariance matrix of the noise. It is shown in this paper that many existing closed-loop identification methods do not give a consistent estimate of the noise covariance matrix. As a result, we propose an alternative subspace formulation for the joint input–output closed-loop identification for which the consistency of the required subspace matrices and noise covariance is guaranteed. Simulation studies and experimental results are provided to demonstrate the utility of the proposed method.

[1]  W. Larimore.  System Identification, Reduced-Order Filtering and Modeling via Canonical Variate Analysis , 1983, 1983 American Control Conference.

[2]  B. Moor,et al.  Closed loop subspace system identification , 1997 .

[3]  Alessandro Chiuso,et al.  Consistency analysis of some closed-loop subspace identification methods , 2005, Autom..

[4]  S. Joe Qin,et al.  Control performance monitoring — a review and assessment , 1998 .

[5]  Lennart Ljung,et al.  Parallel QR Implementation of Subspace Identification with Parsimonious Models , 2003 .

[6]  T. Harris,et al.  Performance assessment measures for univariate feedback control , 1992 .

[7]  T. Harris.  Assessment of Control Loop Performance , 1989 .

[8]  S. Ding,et al.  Closed-loop subspace identification: an orthogonal projection approach , 2004 .

[9]  B. Moor,et al.  Subspace identification for linear systems , 1996 .

[10]  Riccardo Marino,et al.  Nonlinear control design , 1995 .

[11]  Manfred Deistler,et al.  Consistency and relative efficiency of subspace methods , 1994, Autom..

[12]  M. Moonen,et al.  On- and off-line identification of linear state-space models , 1989 .

[13]  Bart De Moor,et al.  Subspace Identification for Linear Systems: Theory ― Implementation ― Applications , 2011 .

[14]  D. Ender.  Process Control Performance : Not as Good as You Think , 1993 .

[15]  Lennart Ljung,et al.  Subspace identification from closed loop data , 1996, Signal Process..

[16]  Jin Wang,et al.  Closed-loop subspace identification using the parity space , 2006, Autom..

[17]  Tohru Katayama,et al.  An approach to closed-loop subspace identification by orthogonal decomposition , 2007, Autom..

[18]  Bo Wahlberg,et al.  On Consistency of Subspace Methods for System Identification , 1998, Autom..

[19]  Biao Huang,et al.  Controller performance analysis with LQG benchmark obtained under closed loop conditions. , 2002, ISA transactions.

[20]  Thomas F. Edgar,et al.  Performance assessment of constrained model predictive control systems , 2001 .

[21]  Bart De Moor,et al.  Choice of state-space basis in combined deterministic-stochastic subspace identification , 1995, Autom..

[22]  Nina F. Thornhill,et al.  Refinery-wide control loop performance assessment , 1999 .

[23]  Bart De Moor,et al.  A unifying theorem for three subspace system identification algorithms , 1995, Autom..

[24]  L. Ljung,et al.  On consistency of closed-loop subspace identification with innovation estimation , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[25]  Sirish L. Shah,et al.  The unitary interactor matrix and its estimation using closed-loop data , 1997 .

[26]  S. Joe Qin,et al.  Recent developments in multivariable controller performance monitoring , 2007 .

[27]  Dietmar Bauer,et al.  Consistency and asymptotic normality of some subspace algorithms for systems without observed inputs , 1999, Autom..

[28]  Sirish L. Shah,et al.  Good, bad or optimal? Performance assessment of multivariable processes , 1997, Autom..

[29]  Dietmar Bauer,et al.  Analysis of the asymptotic properties of the MOESP type of subspace algorithms , 2000, Autom..

[30]  Ali Cinar,et al.  Multivariable MPC system performance assessment, monitoring, and diagnosis , 2004 .

[31]  Max Donath,et al.  American Control Conference , 1993 .

[32]  Alessandro Chiuso,et al.  Consistency analysis of closed-loop subspace identification , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[33]  Bart De Moor,et al.  N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems , 1994, Autom..

[34]  Alessandro Chiuso.  Asymptotic variance of closed-loop subspace identification methods , 2006, IEEE Transactions on Automatic Control.

[35]  C. T. Seppala,et al.  A review of performance monitoring and assessment techniques for univariate and multivariate control systems , 1999 .

[36]  Wallace E. Larimore,et al.  Statistical optimality and canonical variate analysis system identification , 1996, Signal Process..

[37]  S. Qin,et al.  Projection based MIMO control performance monitoring: I—covariance monitoring in state space , 2003 .

[38]  Patrick Dewilde,et al.  Subspace model identification Part 1. The output-error state-space model identification class of algorithms , 1992 .

[39]  Michel Verhaegen,et al.  Application of a subspace model identification technique to identify LTI systems operating in closed-loop , 1993, Autom..

[40]  D. Bauer.  Some asymptotic theory for the estimation of linear systems using maximum likelihood methods or subspace algorithms , 1998 .

[41]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[42]  T. J. Harris,et al.  Performance assessment of multivariable feedback controllers , 1996, Autom..

[43]  Michael J. Piovoso,et al.  Process and controller performance monitoring: overview with industrial applications , 2003 .

[44]  S. Joe Qin,et al.  Statistical MIMO controller performance monitoring. Part I: Data-driven covariance benchmark , 2008 .

[45]  Biao Huang,et al.  Estimation of the Dynamic Matrix and Noise Model for Model Predictive Control Using Closed-Loop Data , 2002 .

[46]  Christopher Alan McNabb.  MIMO control performance monitoring based on subspace projections , 2002 .

[47]  Lennart Ljung,et al.  Closed-Loop Subspace Identification with Innovation Estimation , 2003 .

[48]  Manfred Deistler,et al.  Statistical analysis of novel subspace identification methods , 1996, Signal Process..

[49]  Dietmar Bauer,et al.  Asymptotic properties of subspace estimators , 2005, Autom..

[50]  Torben Knudsen.  Consistency analysis of subspace identification methods based on a linear regression approach , 2001, Autom..

[51]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .